Implementasi Deteksi Objek Pada Jalan Rusak Menggunakan Metode YOLOv8

Abstract

Roads are an essential transportation infrastructure that connects one place to another. Roads also have a significant impact on the development of a region because land transportation relies on roads to transport essential goods needed by the community, such as clothing and food. The dataset used consists of 26,336 images, divided into 80% training data, 10% validation data, and 10% test data. This software development aims to detect damaged road types using the YOLOv8 algorithm. The testing results showed that the best accuracy was achieved using 100 epochs, with an accuracy of 43.98%.